Automated Ticket Resolution Using Machine Learning Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional ticket submission systems require significant human intervention and resources for manual issue identification and solution determination, leading to inefficiencies and prolonged downtime in resolving computing system issues.
Innovation Solution
An automated ticket resolution system that trains machine-learning-based classifier and solution models using ticket database records to automatically determine problem statements and predict solutions, with implementation based on certainty characteristics, allowing for either automated or human-assisted execution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual ticket evaluation and resolution is used, then human representatives can determine appropriate solutions, but significant human intervention and resources are required leading to inefficiencies and prolonged downtime
Solution Approach 1:
The system enables automated self-service ticket resolution by training machine learning models to independently evaluate tickets, generate problem statements, predict solutions, and implement resolutions without human intervention. The model autonomously processes ticket data, accesses relevant information from databases, and executes corrective actions based on predicted solutions, allowing the system to resolve issues independently.
Solution Approach 2:
The patent replaces the mechanical human decision-making process with an automated machine learning system. The model substitutes human representatives by automatically performing ticket evaluation, solution determination, and implementation tasks that previously required manual human intervention, thereby eliminating the bottleneck of human processing speed while maintaining solution quality.
2Ease of operation
If manual ticket processing is used, then human representatives can assess and resolve issues, but resource expenditure and downtime increase
Solution Approach 1:
The system performs preliminary actions by pre-training the machine learning model on extensive ticket data and solution databases before actual ticket resolution. The model is prepared in advance with knowledge of common issues, solutions, and system configurations, enabling it to quickly process and resolve tickets without requiring real-time human analysis or decision-making.
Solution Approach 2:
The machine learning model acts as an intermediary between ticket submission and resolution implementation. It receives ticket data, automatically generates problem statements, predicts appropriate solutions by querying databases, and executes resolutions, serving as an automated mediator that eliminates the need for direct human intervention in the ticket processing workflow.
3Productivity
If automated machine-learning-based resolution is implemented, then resource expenditure and downtime are reduced, but the system requires training data and model development
Solution Approach 1:
The machine learning model is designed with universal functionality to handle multiple types of tickets across different system components and issues. By training on diverse ticket data and solution databases, the model becomes a multi-functional system that can resolve various types of problems using the same automated framework, reducing the need for separate specialized systems for different ticket categories.
Data Source
AI summary
A method of automated ticket resolution comprises training and testing feature-specific classifier models using ticket database records. The feature-specific classifier models include machine-learning-based classification models related to features of a ticket system. The method includes training and testing feature-specific solution models using resolved ticket solution database records. The feature-specific classifier models include machine-learning-based solution models related to the features. The method includes receiving a ticket inquiry including a ticket indicative of an issue related to the features, generating a problem statement representative of the issue using the tested classifier models, and communicating the problem statement to the tested solution models. The method includes predicting a solution to the problem statement by using the tested solution models. The solution includes directions to resolve the ticket. The method includes implementing the solution in the system to resolve the issue based on certainty characteristics of the solution and recover a system if required.